skip to content
shailesh jm
Home
Posts
Tags
Showcase
Writing · 5 posts
Oct 23, 2026
When Does a Time Series Contain Predictive Information?
time-series
·
statistics
·
forecasting
Oct 22, 2026
Decomposing Time Series: From Moving Averages to STL
time-series
·
statistics
·
forecasting
Oct 12, 2026
Why Do Transformers Divide Attention Scores by √d?
nlp
·
transformers
·
mathematics
Sep 29, 2026
Why Adam Works: From Gradient Descent to Adaptive Optimization
deep-learning
·
optimization
·
mathematics
Sep 15, 2026
Word2Vec, Negative Sampling, and the Geometry of Meaning
nlp
·
embeddings
·
deep-learning